Merge branch 'ggerganov:master' into master
This commit is contained in:
Zhiyuan Li
GitHub
commit
acb1b9d22c
6 changed files with 455 additions and 458 deletions
|
|
@ -692,7 +692,10 @@ Given a ChatML-formatted json description in `messages`, it returns the predicte
|
|||
|
||||
### GET `/slots`: Returns the current slots processing state
|
||||
|
||||
This endpoint can be disabled with `--no-slots`
|
||||
> [!WARNING]
|
||||
> This endpoint is intended for debugging and may be modified in future versions. For security reasons, we strongly advise against enabling it in production environments.
|
||||
|
||||
This endpoint is disabled by default and can be enabled with `--slots`
|
||||
|
||||
If query param `?fail_on_no_slot=1` is set, this endpoint will respond with status code 503 if there is no available slots.
|
||||
|
||||
|
|
@ -709,6 +712,7 @@ Example:
|
|||
"grammar": "",
|
||||
"id": 0,
|
||||
"ignore_eos": false,
|
||||
"is_processing": false,
|
||||
"logit_bias": [],
|
||||
"min_p": 0.05000000074505806,
|
||||
"mirostat": 0,
|
||||
|
|
@ -741,7 +745,6 @@ Example:
|
|||
"temperature"
|
||||
],
|
||||
"seed": 42,
|
||||
"state": 1,
|
||||
"stop": [
|
||||
"\n"
|
||||
],
|
||||
|
|
@ -755,10 +758,6 @@ Example:
|
|||
]
|
||||
```
|
||||
|
||||
Possible values for `slot[i].state` are:
|
||||
- `0`: SLOT_STATE_IDLE
|
||||
- `1`: SLOT_STATE_PROCESSING
|
||||
|
||||
### GET `/metrics`: Prometheus compatible metrics exporter
|
||||
|
||||
This endpoint is only accessible if `--metrics` is set.
|
||||
|
|
|
|||
|
|
@ -1566,11 +1566,11 @@ struct server_context {
|
|||
|
||||
for (server_slot & slot : slots) {
|
||||
json slot_data = get_formated_generation(slot);
|
||||
slot_data["id"] = slot.id;
|
||||
slot_data["id_task"] = slot.id_task;
|
||||
slot_data["state"] = slot.state;
|
||||
slot_data["prompt"] = common_detokenize(ctx, slot.prompt_tokens);
|
||||
slot_data["next_token"] = {
|
||||
slot_data["id"] = slot.id;
|
||||
slot_data["id_task"] = slot.id_task;
|
||||
slot_data["is_processing"] = slot.is_processing();
|
||||
slot_data["prompt"] = common_detokenize(ctx, slot.prompt_tokens);
|
||||
slot_data["next_token"] = {
|
||||
{"has_next_token", slot.has_next_token},
|
||||
{"has_new_line", slot.has_new_line},
|
||||
{"n_remain", slot.n_remaining},
|
||||
|
|
@ -1581,10 +1581,10 @@ struct server_context {
|
|||
{"stopping_word", slot.stopping_word},
|
||||
};
|
||||
|
||||
if (slot_data["state"] == SLOT_STATE_IDLE) {
|
||||
n_idle_slots++;
|
||||
} else {
|
||||
if (slot.is_processing()) {
|
||||
n_processing_slots++;
|
||||
} else {
|
||||
n_idle_slots++;
|
||||
}
|
||||
|
||||
slots_data.push_back(slot_data);
|
||||
|
|
|
|||
|
|
@ -260,13 +260,13 @@ async def step_wait_for_server_status(context, expecting_status: Literal['health
|
|||
async def step_all_slots_status(context, expected_slot_status_string: Literal['idle', 'busy'] | str):
|
||||
match expected_slot_status_string:
|
||||
case 'idle':
|
||||
expected_slot_status = 0
|
||||
expected_slot_status = False
|
||||
case 'busy':
|
||||
expected_slot_status = 1
|
||||
expected_slot_status = True
|
||||
case _:
|
||||
assert False, "unknown status"
|
||||
|
||||
expected_slots = [{'id': slot_id, 'state': expected_slot_status}
|
||||
expected_slots = [{'id': slot_id, 'is_processing': expected_slot_status}
|
||||
for slot_id in range(context.n_slots)]
|
||||
await request_slots_status(context, expected_slots)
|
||||
|
||||
|
|
@ -1354,8 +1354,8 @@ async def wait_for_slots_status(context,
|
|||
if status_code == 503 and status_code == expected_http_status_code:
|
||||
return
|
||||
if status_code == 200 and status_code == expected_http_status_code:
|
||||
n_slots_idle = sum(1 if slot["state"] == 0 else 0 for slot in slots)
|
||||
n_slots_processing = sum(1 if slot["state"] != 0 else 0 for slot in slots)
|
||||
n_slots_idle = sum(1 if not slot["is_processing"] else 0 for slot in slots)
|
||||
n_slots_processing = sum(1 if slot["is_processing"] else 0 for slot in slots)
|
||||
if ((slots_idle is None or slots_idle == n_slots_idle)
|
||||
and (slots_processing is None or slots_processing == n_slots_processing)):
|
||||
return
|
||||
|
|
|
|||
|
|
@ -1297,11 +1297,17 @@ static void ggml_cuda_set_peer_access(const int n_tokens, int main_device) {
|
|||
cudaError_t err = cudaDeviceEnablePeerAccess(id_other, 0);
|
||||
if (err != cudaErrorPeerAccessAlreadyEnabled) {
|
||||
CUDA_CHECK(err);
|
||||
} else {
|
||||
// reset the error
|
||||
cudaGetLastError();
|
||||
}
|
||||
} else {
|
||||
cudaError_t err = cudaDeviceDisablePeerAccess(id_other);
|
||||
if (err != cudaErrorPeerAccessNotEnabled) {
|
||||
CUDA_CHECK(err);
|
||||
} else {
|
||||
// reset the error
|
||||
cudaGetLastError();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -12,6 +12,436 @@ using namespace metal;
|
|||
|
||||
#define N_SIMDWIDTH 32 // assuming SIMD group size is 32
|
||||
|
||||
constexpr constant static float kvalues_iq4nl_f[16] = {
|
||||
-127.f, -104.f, -83.f, -65.f, -49.f, -35.f, -22.f, -10.f, 1.f, 13.f, 25.f, 38.f, 53.f, 69.f, 89.f, 113.f
|
||||
};
|
||||
|
||||
// NOTE: this is not dequantizing - we are simply fitting the template
|
||||
template <typename type4x4>
|
||||
void dequantize_f32(device const float4x4 * src, short il, thread type4x4 & reg) {
|
||||
reg = (type4x4)(*src);
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_f16(device const half4x4 * src, short il, thread type4x4 & reg) {
|
||||
reg = (type4x4)(*src);
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q4_0(device const block_q4_0 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 1);
|
||||
const float d1 = il ? (xb->d / 16.h) : xb->d;
|
||||
const float d2 = d1 / 256.f;
|
||||
const float md = -8.h * xb->d;
|
||||
const ushort mask0 = il ? 0x00F0 : 0x000F;
|
||||
const ushort mask1 = mask0 << 8;
|
||||
|
||||
for (int i=0;i<8;i++) {
|
||||
reg[i/2][2*(i%2)+0] = d1 * (qs[i] & mask0) + md;
|
||||
reg[i/2][2*(i%2)+1] = d2 * (qs[i] & mask1) + md;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q4_1(device const block_q4_1 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 2);
|
||||
const float d1 = il ? (xb->d / 16.h) : xb->d;
|
||||
const float d2 = d1 / 256.f;
|
||||
const float m = xb->m;
|
||||
const ushort mask0 = il ? 0x00F0 : 0x000F;
|
||||
const ushort mask1 = mask0 << 8;
|
||||
|
||||
for (int i=0;i<8;i++) {
|
||||
reg[i/2][2*(i%2)+0] = ((qs[i] & mask0) * d1) + m;
|
||||
reg[i/2][2*(i%2)+1] = ((qs[i] & mask1) * d2) + m;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q5_0(device const block_q5_0 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 3);
|
||||
const float d = xb->d;
|
||||
const float md = -16.h * xb->d;
|
||||
const ushort mask = il ? 0x00F0 : 0x000F;
|
||||
|
||||
const uint32_t qh = *((device const uint32_t *)xb->qh);
|
||||
|
||||
const int x_mv = il ? 4 : 0;
|
||||
|
||||
const int gh_mv = il ? 12 : 0;
|
||||
const int gh_bk = il ? 0 : 4;
|
||||
|
||||
for (int i = 0; i < 8; i++) {
|
||||
// extract the 5-th bits for x0 and x1
|
||||
const uint8_t xh_0 = ((qh >> (gh_mv + 2*i )) << gh_bk) & 0x10;
|
||||
const uint8_t xh_1 = ((qh >> (gh_mv + 2*i+1)) << gh_bk) & 0x10;
|
||||
|
||||
// combine the 4-bits from qs with the 5th bit
|
||||
const int32_t x0 = ((((qs[i] ) & mask) >> x_mv) | xh_0);
|
||||
const int32_t x1 = ((((qs[i] >> 8) & mask) >> x_mv) | xh_1);
|
||||
|
||||
reg[i/2][2*(i%2)+0] = d * x0 + md;
|
||||
reg[i/2][2*(i%2)+1] = d * x1 + md;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q5_1(device const block_q5_1 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 4);
|
||||
const float d = xb->d;
|
||||
const float m = xb->m;
|
||||
const ushort mask = il ? 0x00F0 : 0x000F;
|
||||
|
||||
const uint32_t qh = *((device const uint32_t *)xb->qh);
|
||||
|
||||
const int x_mv = il ? 4 : 0;
|
||||
|
||||
const int gh_mv = il ? 12 : 0;
|
||||
const int gh_bk = il ? 0 : 4;
|
||||
|
||||
for (int i = 0; i < 8; i++) {
|
||||
// extract the 5-th bits for x0 and x1
|
||||
const uint8_t xh_0 = ((qh >> (gh_mv + 2*i )) << gh_bk) & 0x10;
|
||||
const uint8_t xh_1 = ((qh >> (gh_mv + 2*i+1)) << gh_bk) & 0x10;
|
||||
|
||||
// combine the 4-bits from qs with the 5th bit
|
||||
const int32_t x0 = ((((qs[i] ) & mask) >> x_mv) | xh_0);
|
||||
const int32_t x1 = ((((qs[i] >> 8) & mask) >> x_mv) | xh_1);
|
||||
|
||||
reg[i/2][2*(i%2)+0] = d * x0 + m;
|
||||
reg[i/2][2*(i%2)+1] = d * x1 + m;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q8_0(device const block_q8_0 *xb, short il, thread type4x4 & reg) {
|
||||
device const int8_t * qs = ((device const int8_t *)xb->qs);
|
||||
const half d = xb->d;
|
||||
|
||||
for (int i = 0; i < 16; i++) {
|
||||
reg[i/4][i%4] = (qs[i + 16*il] * d);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q2_K(device const block_q2_K *xb, short il, thread type4x4 & reg) {
|
||||
const float d = xb->d;
|
||||
const float min = xb->dmin;
|
||||
device const uint8_t * q = (device const uint8_t *)xb->qs;
|
||||
float dl, ml;
|
||||
uint8_t sc = xb->scales[il];
|
||||
|
||||
q = q + 32*(il/8) + 16*(il&1);
|
||||
il = (il/2)%4;
|
||||
|
||||
half coef = il>1 ? (il>2 ? 1/64.h : 1/16.h) : (il>0 ? 1/4.h : 1.h);
|
||||
uchar mask = il>1 ? (il>2 ? 192 : 48) : (il>0 ? 12 : 3);
|
||||
dl = d * (sc & 0xF) * coef, ml = min * (sc >> 4);
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * (q[i] & mask) - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q3_K(device const block_q3_K *xb, short il, thread type4x4 & reg) {
|
||||
const half d_all = xb->d;
|
||||
device const uint8_t * q = (device const uint8_t *)xb->qs;
|
||||
device const uint8_t * h = (device const uint8_t *)xb->hmask;
|
||||
device const int8_t * scales = (device const int8_t *)xb->scales;
|
||||
|
||||
q = q + 32 * (il/8) + 16 * (il&1);
|
||||
h = h + 16 * (il&1);
|
||||
uint8_t m = 1 << (il/2);
|
||||
uint16_t kmask1 = (il/4)>1 ? ((il/4)>2 ? 192 : 48) : \
|
||||
((il/4)>0 ? 12 : 3);
|
||||
uint16_t kmask2 = il/8 ? 0xF0 : 0x0F;
|
||||
uint16_t scale_2 = scales[il%8], scale_1 = scales[8 + il%4];
|
||||
int16_t dl_int = (il/4)&1 ? (scale_2&kmask2) | ((scale_1&kmask1) << 2)
|
||||
: (scale_2&kmask2) | ((scale_1&kmask1) << 4);
|
||||
float dl = il<8 ? d_all * (dl_int - 32.f) : d_all * (dl_int / 16.f - 32.f);
|
||||
const float ml = 4.f * dl;
|
||||
|
||||
il = (il/2) & 3;
|
||||
const half coef = il>1 ? (il>2 ? 1/64.h : 1/16.h) : (il>0 ? 1/4.h : 1.h);
|
||||
const uint8_t mask = il>1 ? (il>2 ? 192 : 48) : (il>0 ? 12 : 3);
|
||||
dl *= coef;
|
||||
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * (q[i] & mask) - (h[i] & m ? 0 : ml);
|
||||
}
|
||||
}
|
||||
|
||||
static inline uchar2 get_scale_min_k4_just2(int j, int k, device const uchar * q) {
|
||||
return j < 4 ? uchar2{uchar(q[j+0+k] & 63), uchar(q[j+4+k] & 63)}
|
||||
: uchar2{uchar((q[j+4+k] & 0xF) | ((q[j-4+k] & 0xc0) >> 2)), uchar((q[j+4+k] >> 4) | ((q[j-0+k] & 0xc0) >> 2))};
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q4_K(device const block_q4_K *xb, short il, thread type4x4 & reg) {
|
||||
device const uchar * q = xb->qs;
|
||||
|
||||
short is = (il/4) * 2;
|
||||
q = q + (il/4) * 32 + 16 * (il&1);
|
||||
il = il & 3;
|
||||
const uchar2 sc = get_scale_min_k4_just2(is, il/2, xb->scales);
|
||||
const float d = il < 2 ? xb->d : xb->d / 16.h;
|
||||
const float min = xb->dmin;
|
||||
const float dl = d * sc[0];
|
||||
const float ml = min * sc[1];
|
||||
|
||||
const ushort mask = il<2 ? 0x0F : 0xF0;
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * (q[i] & mask) - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q5_K(device const block_q5_K *xb, short il, thread type4x4 & reg) {
|
||||
device const uint8_t * q = xb->qs;
|
||||
device const uint8_t * qh = xb->qh;
|
||||
|
||||
short is = (il/4) * 2;
|
||||
q = q + 32 * (il/4) + 16 * (il&1);
|
||||
qh = qh + 16 * (il&1);
|
||||
uint8_t ul = 1 << (il/2);
|
||||
il = il & 3;
|
||||
const uchar2 sc = get_scale_min_k4_just2(is, il/2, xb->scales);
|
||||
const float d = il < 2 ? xb->d : xb->d / 16.f;
|
||||
const float min = xb->dmin;
|
||||
const float dl = d * sc[0];
|
||||
const float ml = min * sc[1];
|
||||
|
||||
const ushort mask = il<2 ? 0x0F : 0xF0;
|
||||
const float qh_val = il<2 ? 16.f : 256.f;
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * ((q[i] & mask) + (qh[i] & ul ? qh_val : 0)) - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q6_K(device const block_q6_K *xb, short il, thread type4x4 & reg) {
|
||||
const half d_all = xb->d;
|
||||
device const uint8_t * ql = (device const uint8_t *)xb->ql;
|
||||
device const uint8_t * qh = (device const uint8_t *)xb->qh;
|
||||
device const int8_t * scales = (device const int8_t *)xb->scales;
|
||||
|
||||
ql = ql + 64*(il/8) + 32*((il/2)&1) + 16*(il&1);
|
||||
qh = qh + 32*(il/8) + 16*(il&1);
|
||||
float sc = scales[(il%2) + 2 * ((il/2))];
|
||||
il = (il/2) & 3;
|
||||
|
||||
const uint16_t kmask1 = il>1 ? (il>2 ? 192 : 48) : (il>0 ? 12 : 3);
|
||||
const uint16_t kmask2 = il>1 ? 0xF0 : 0x0F;
|
||||
const float coef = il>1 ? 1.f/16.f : 1.f;
|
||||
const float ml = d_all * sc * 32.f;
|
||||
const float dl = d_all * sc * coef;
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
const half q = il&1 ? ((ql[i] & kmask2) | ((qh[i] & kmask1) << 2))
|
||||
: ((ql[i] & kmask2) | ((qh[i] & kmask1) << 4));
|
||||
reg[i/4][i%4] = dl * q - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq2_xxs(device const block_iq2_xxs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
// each block of 32 needs 2 uint32_t's for the quants & scale, so 4 uint16_t's.
|
||||
device const uint16_t * q2 = xb->qs + 4*ib32;
|
||||
const uint32_t aux32_g = q2[0] | (q2[1] << 16);
|
||||
const uint32_t aux32_s = q2[2] | (q2[3] << 16);
|
||||
thread const uint8_t * aux8 = (thread const uint8_t *)&aux32_g;
|
||||
const float dl = d * (0.5f + (aux32_s >> 28)) * 0.25f;
|
||||
constant uint8_t * grid = (constant uint8_t *)(iq2xxs_grid + aux8[2*il+0]);
|
||||
uint8_t signs = ksigns_iq2xs[(aux32_s >> 14*il) & 127];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
grid = (constant uint8_t *)(iq2xxs_grid + aux8[2*il+1]);
|
||||
signs = ksigns_iq2xs[(aux32_s >> (14*il+7)) & 127];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[2+i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq2_xs(device const block_iq2_xs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint16_t * q2 = xb->qs + 4*ib32;
|
||||
const float dl = d * (0.5f + ((xb->scales[ib32] >> 4*il) & 0xf)) * 0.25f;
|
||||
constant uint8_t * grid = (constant uint8_t *)(iq2xs_grid + (q2[2*il+0] & 511));
|
||||
uint8_t signs = ksigns_iq2xs[q2[2*il+0] >> 9];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
grid = (constant uint8_t *)(iq2xs_grid + (q2[2*il+1] & 511));
|
||||
signs = ksigns_iq2xs[q2[2*il+1] >> 9];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[2+i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq3_xxs(device const block_iq3_xxs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint8_t * q3 = xb->qs + 8*ib32;
|
||||
device const uint16_t * gas = (device const uint16_t *)(xb->qs + QK_K/4) + 2*ib32;
|
||||
const uint32_t aux32 = gas[0] | (gas[1] << 16);
|
||||
const float dl = d * (0.5f + (aux32 >> 28)) * 0.5f;
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+0]);
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+1]);
|
||||
uint8_t signs = ksigns_iq2xs[(aux32 >> 14*il) & 127];
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * grid1[i] * (signs & kmask_iq2xs[i+0] ? -1.f : 1.f);
|
||||
reg[1][i] = dl * grid2[i] * (signs & kmask_iq2xs[i+4] ? -1.f : 1.f);
|
||||
}
|
||||
grid1 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+2]);
|
||||
grid2 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+3]);
|
||||
signs = ksigns_iq2xs[(aux32 >> (14*il+7)) & 127];
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[2][i] = dl * grid1[i] * (signs & kmask_iq2xs[i+0] ? -1.f : 1.f);
|
||||
reg[3][i] = dl * grid2[i] * (signs & kmask_iq2xs[i+4] ? -1.f : 1.f);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq3_s(device const block_iq3_s * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint8_t * qs = xb->qs + 8*ib32;
|
||||
device const uint8_t * signs = xb->signs + 4*ib32 + 2*il;
|
||||
const uint8_t qh = xb->qh[ib32] >> 4*il;
|
||||
const float dl = d * (1 + 2*((xb->scales[ib32/2] >> 4*(ib32%2)) & 0xf));
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq3s_grid + (qs[4*il+0] | ((qh << 8) & 256)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq3s_grid + (qs[4*il+1] | ((qh << 7) & 256)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * grid1[i] * select(1, -1, signs[0] & kmask_iq2xs[i+0]);
|
||||
reg[1][i] = dl * grid2[i] * select(1, -1, signs[0] & kmask_iq2xs[i+4]);
|
||||
}
|
||||
grid1 = (constant uint8_t *)(iq3s_grid + (qs[4*il+2] | ((qh << 6) & 256)));
|
||||
grid2 = (constant uint8_t *)(iq3s_grid + (qs[4*il+3] | ((qh << 5) & 256)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[2][i] = dl * grid1[i] * select(1, -1, signs[1] & kmask_iq2xs[i+0]);
|
||||
reg[3][i] = dl * grid2[i] * select(1, -1, signs[1] & kmask_iq2xs[i+4]);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq2_s(device const block_iq2_s * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint8_t * qs = xb->qs + 4*ib32 + 2*il;
|
||||
device const uint8_t * signs = qs + QK_K/8;
|
||||
const uint8_t qh = xb->qh[ib32] >> 4*il;
|
||||
const float dl = d * (0.5f + ((xb->scales[ib32] >> 4*il) & 0xf)) * 0.25f;
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq2s_grid + (qs[0] | ((qh << 8) & 0x300)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq2s_grid + (qs[1] | ((qh << 6) & 0x300)));
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4+0][i%4] = dl * grid1[i] * select(1, -1, signs[0] & kmask_iq2xs[i]);
|
||||
reg[i/4+2][i%4] = dl * grid2[i] * select(1, -1, signs[1] & kmask_iq2xs[i]);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq1_s(device const block_iq1_s * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
const float d = xb->d;
|
||||
device const uint8_t * qs = xb->qs + 4*ib32 + 2*il;
|
||||
device const uint16_t * qh = xb->qh;
|
||||
const float dl = d * (2*((qh[ib32] >> 12) & 7) + 1);
|
||||
const float ml = dl * (qh[ib32] & 0x8000 ? -1 - IQ1S_DELTA : -1 + IQ1S_DELTA);
|
||||
const uint16_t h = qh[ib32] >> 6*il;
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((h << 8) & 0x700)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((h << 5) & 0x700)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * (grid1[i] & 0xf) + ml;
|
||||
reg[1][i] = dl * (grid1[i] >> 4) + ml;
|
||||
reg[2][i] = dl * (grid2[i] & 0xf) + ml;
|
||||
reg[3][i] = dl * (grid2[i] >> 4) + ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq1_m(device const block_iq1_m * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
device const uint16_t * sc = (device const uint16_t *)xb->scales;
|
||||
|
||||
iq1m_scale_t scale;
|
||||
scale.u16 = (sc[0] >> 12) | ((sc[1] >> 8) & 0x00f0) | ((sc[2] >> 4) & 0x0f00) | (sc[3] & 0xf000);
|
||||
const float d = scale.f16;
|
||||
|
||||
device const uint8_t * qs = xb->qs + 4*ib32 + 2*il;
|
||||
device const uint8_t * qh = xb->qh + 2*ib32 + il;
|
||||
|
||||
const float dl = d * (2*((sc[ib32/2] >> (6*(ib32%2)+3*il)) & 7) + 1);
|
||||
const float ml1 = dl * (qh[0] & 0x08 ? -1 - IQ1M_DELTA : -1 + IQ1M_DELTA);
|
||||
const float ml2 = dl * (qh[0] & 0x80 ? -1 - IQ1M_DELTA : -1 + IQ1M_DELTA);
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((qh[0] << 8) & 0x700)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((qh[0] << 4) & 0x700)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * (grid1[i] & 0xf) + ml1;
|
||||
reg[1][i] = dl * (grid1[i] >> 4) + ml1;
|
||||
reg[2][i] = dl * (grid2[i] & 0xf) + ml2;
|
||||
reg[3][i] = dl * (grid2[i] >> 4) + ml2;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq4_nl(device const block_iq4_nl * xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * q4 = (device const uint16_t *)xb->qs;
|
||||
const float d = xb->d;
|
||||
uint32_t aux32;
|
||||
thread const uint8_t * q8 = (thread const uint8_t *)&aux32;
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
aux32 = ((q4[2*i] | (q4[2*i+1] << 16)) >> 4*il) & 0x0f0f0f0f;
|
||||
reg[i][0] = d * kvalues_iq4nl_f[q8[0]];
|
||||
reg[i][1] = d * kvalues_iq4nl_f[q8[1]];
|
||||
reg[i][2] = d * kvalues_iq4nl_f[q8[2]];
|
||||
reg[i][3] = d * kvalues_iq4nl_f[q8[3]];
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq4_xs(device const block_iq4_xs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint32_t * q4 = (device const uint32_t *)xb->qs + 4*ib32;
|
||||
const int ls = ((xb->scales_l[ib32/2] >> 4*(ib32%2)) & 0xf) | (((xb->scales_h >> 2*ib32) & 3) << 4);
|
||||
const float d = (float)xb->d * (ls - 32);
|
||||
uint32_t aux32;
|
||||
thread const uint8_t * q8 = (thread const uint8_t *)&aux32;
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
aux32 = (q4[i] >> 4*il) & 0x0f0f0f0f;
|
||||
reg[i][0] = d * kvalues_iq4nl_f[q8[0]];
|
||||
reg[i][1] = d * kvalues_iq4nl_f[q8[1]];
|
||||
reg[i][2] = d * kvalues_iq4nl_f[q8[2]];
|
||||
reg[i][3] = d * kvalues_iq4nl_f[q8[3]];
|
||||
}
|
||||
}
|
||||
|
||||
enum ggml_sort_order {
|
||||
GGML_SORT_ORDER_ASC,
|
||||
GGML_SORT_ORDER_DESC,
|
||||
|
|
@ -3339,10 +3769,6 @@ static inline int best_index_int8(int n, constant float * val, float x) {
|
|||
return x - val[mu-1] < val[mu] - x ? mu-1 : mu;
|
||||
}
|
||||
|
||||
constexpr constant static float kvalues_iq4nl_f[16] = {
|
||||
-127.f, -104.f, -83.f, -65.f, -49.f, -35.f, -22.f, -10.f, 1.f, 13.f, 25.f, 38.f, 53.f, 69.f, 89.f, 113.f
|
||||
};
|
||||
|
||||
kernel void kernel_cpy_f32_iq4_nl(
|
||||
device const float * src0,
|
||||
device void * dst,
|
||||
|
|
@ -5457,440 +5883,6 @@ kernel void kernel_mul_mv_iq4_xs_f32(
|
|||
kernel_mul_mv_iq4_xs_f32_impl(src0, src1, dst, ne00, ne01, ne02, nb01, nb02, nb03, ne10, ne12, nb11, nb12, nb13, ne0, ne1, r2, r3, shared_values, tgpig, tiisg, sgitg);
|
||||
}
|
||||
|
||||
//============================= templates and their specializations =============================
|
||||
|
||||
// NOTE: this is not dequantizing - we are simply fitting the template
|
||||
template <typename type4x4>
|
||||
void dequantize_f32(device const float4x4 * src, short il, thread type4x4 & reg) {
|
||||
float4x4 temp = *(((device float4x4 *)src));
|
||||
for (int i = 0; i < 16; i++){
|
||||
reg[i/4][i%4] = temp[i/4][i%4];
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_f16(device const half4x4 * src, short il, thread type4x4 & reg) {
|
||||
half4x4 temp = *(((device half4x4 *)src));
|
||||
for (int i = 0; i < 16; i++){
|
||||
reg[i/4][i%4] = temp[i/4][i%4];
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q4_0(device const block_q4_0 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 1);
|
||||
const float d1 = il ? (xb->d / 16.h) : xb->d;
|
||||
const float d2 = d1 / 256.f;
|
||||
const float md = -8.h * xb->d;
|
||||
const ushort mask0 = il ? 0x00F0 : 0x000F;
|
||||
const ushort mask1 = mask0 << 8;
|
||||
|
||||
for (int i=0;i<8;i++) {
|
||||
reg[i/2][2*(i%2)+0] = d1 * (qs[i] & mask0) + md;
|
||||
reg[i/2][2*(i%2)+1] = d2 * (qs[i] & mask1) + md;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q4_1(device const block_q4_1 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 2);
|
||||
const float d1 = il ? (xb->d / 16.h) : xb->d;
|
||||
const float d2 = d1 / 256.f;
|
||||
const float m = xb->m;
|
||||
const ushort mask0 = il ? 0x00F0 : 0x000F;
|
||||
const ushort mask1 = mask0 << 8;
|
||||
|
||||
for (int i=0;i<8;i++) {
|
||||
reg[i/2][2*(i%2)+0] = ((qs[i] & mask0) * d1) + m;
|
||||
reg[i/2][2*(i%2)+1] = ((qs[i] & mask1) * d2) + m;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q5_0(device const block_q5_0 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 3);
|
||||
const float d = xb->d;
|
||||
const float md = -16.h * xb->d;
|
||||
const ushort mask = il ? 0x00F0 : 0x000F;
|
||||
|
||||
const uint32_t qh = *((device const uint32_t *)xb->qh);
|
||||
|
||||
const int x_mv = il ? 4 : 0;
|
||||
|
||||
const int gh_mv = il ? 12 : 0;
|
||||
const int gh_bk = il ? 0 : 4;
|
||||
|
||||
for (int i = 0; i < 8; i++) {
|
||||
// extract the 5-th bits for x0 and x1
|
||||
const uint8_t xh_0 = ((qh >> (gh_mv + 2*i )) << gh_bk) & 0x10;
|
||||
const uint8_t xh_1 = ((qh >> (gh_mv + 2*i+1)) << gh_bk) & 0x10;
|
||||
|
||||
// combine the 4-bits from qs with the 5th bit
|
||||
const int32_t x0 = ((((qs[i] ) & mask) >> x_mv) | xh_0);
|
||||
const int32_t x1 = ((((qs[i] >> 8) & mask) >> x_mv) | xh_1);
|
||||
|
||||
reg[i/2][2*(i%2)+0] = d * x0 + md;
|
||||
reg[i/2][2*(i%2)+1] = d * x1 + md;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q5_1(device const block_q5_1 *xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * qs = ((device const uint16_t *)xb + 4);
|
||||
const float d = xb->d;
|
||||
const float m = xb->m;
|
||||
const ushort mask = il ? 0x00F0 : 0x000F;
|
||||
|
||||
const uint32_t qh = *((device const uint32_t *)xb->qh);
|
||||
|
||||
const int x_mv = il ? 4 : 0;
|
||||
|
||||
const int gh_mv = il ? 12 : 0;
|
||||
const int gh_bk = il ? 0 : 4;
|
||||
|
||||
for (int i = 0; i < 8; i++) {
|
||||
// extract the 5-th bits for x0 and x1
|
||||
const uint8_t xh_0 = ((qh >> (gh_mv + 2*i )) << gh_bk) & 0x10;
|
||||
const uint8_t xh_1 = ((qh >> (gh_mv + 2*i+1)) << gh_bk) & 0x10;
|
||||
|
||||
// combine the 4-bits from qs with the 5th bit
|
||||
const int32_t x0 = ((((qs[i] ) & mask) >> x_mv) | xh_0);
|
||||
const int32_t x1 = ((((qs[i] >> 8) & mask) >> x_mv) | xh_1);
|
||||
|
||||
reg[i/2][2*(i%2)+0] = d * x0 + m;
|
||||
reg[i/2][2*(i%2)+1] = d * x1 + m;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q8_0(device const block_q8_0 *xb, short il, thread type4x4 & reg) {
|
||||
device const int8_t * qs = ((device const int8_t *)xb->qs);
|
||||
const half d = xb->d;
|
||||
|
||||
for (int i = 0; i < 16; i++) {
|
||||
reg[i/4][i%4] = (qs[i + 16*il] * d);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q2_K(device const block_q2_K *xb, short il, thread type4x4 & reg) {
|
||||
const float d = xb->d;
|
||||
const float min = xb->dmin;
|
||||
device const uint8_t * q = (device const uint8_t *)xb->qs;
|
||||
float dl, ml;
|
||||
uint8_t sc = xb->scales[il];
|
||||
|
||||
q = q + 32*(il/8) + 16*(il&1);
|
||||
il = (il/2)%4;
|
||||
|
||||
half coef = il>1 ? (il>2 ? 1/64.h : 1/16.h) : (il>0 ? 1/4.h : 1.h);
|
||||
uchar mask = il>1 ? (il>2 ? 192 : 48) : (il>0 ? 12 : 3);
|
||||
dl = d * (sc & 0xF) * coef, ml = min * (sc >> 4);
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * (q[i] & mask) - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q3_K(device const block_q3_K *xb, short il, thread type4x4 & reg) {
|
||||
const half d_all = xb->d;
|
||||
device const uint8_t * q = (device const uint8_t *)xb->qs;
|
||||
device const uint8_t * h = (device const uint8_t *)xb->hmask;
|
||||
device const int8_t * scales = (device const int8_t *)xb->scales;
|
||||
|
||||
q = q + 32 * (il/8) + 16 * (il&1);
|
||||
h = h + 16 * (il&1);
|
||||
uint8_t m = 1 << (il/2);
|
||||
uint16_t kmask1 = (il/4)>1 ? ((il/4)>2 ? 192 : 48) : \
|
||||
((il/4)>0 ? 12 : 3);
|
||||
uint16_t kmask2 = il/8 ? 0xF0 : 0x0F;
|
||||
uint16_t scale_2 = scales[il%8], scale_1 = scales[8 + il%4];
|
||||
int16_t dl_int = (il/4)&1 ? (scale_2&kmask2) | ((scale_1&kmask1) << 2)
|
||||
: (scale_2&kmask2) | ((scale_1&kmask1) << 4);
|
||||
float dl = il<8 ? d_all * (dl_int - 32.f) : d_all * (dl_int / 16.f - 32.f);
|
||||
const float ml = 4.f * dl;
|
||||
|
||||
il = (il/2) & 3;
|
||||
const half coef = il>1 ? (il>2 ? 1/64.h : 1/16.h) : (il>0 ? 1/4.h : 1.h);
|
||||
const uint8_t mask = il>1 ? (il>2 ? 192 : 48) : (il>0 ? 12 : 3);
|
||||
dl *= coef;
|
||||
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * (q[i] & mask) - (h[i] & m ? 0 : ml);
|
||||
}
|
||||
}
|
||||
|
||||
static inline uchar2 get_scale_min_k4_just2(int j, int k, device const uchar * q) {
|
||||
return j < 4 ? uchar2{uchar(q[j+0+k] & 63), uchar(q[j+4+k] & 63)}
|
||||
: uchar2{uchar((q[j+4+k] & 0xF) | ((q[j-4+k] & 0xc0) >> 2)), uchar((q[j+4+k] >> 4) | ((q[j-0+k] & 0xc0) >> 2))};
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q4_K(device const block_q4_K *xb, short il, thread type4x4 & reg) {
|
||||
device const uchar * q = xb->qs;
|
||||
|
||||
short is = (il/4) * 2;
|
||||
q = q + (il/4) * 32 + 16 * (il&1);
|
||||
il = il & 3;
|
||||
const uchar2 sc = get_scale_min_k4_just2(is, il/2, xb->scales);
|
||||
const float d = il < 2 ? xb->d : xb->d / 16.h;
|
||||
const float min = xb->dmin;
|
||||
const float dl = d * sc[0];
|
||||
const float ml = min * sc[1];
|
||||
|
||||
const ushort mask = il<2 ? 0x0F : 0xF0;
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * (q[i] & mask) - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q5_K(device const block_q5_K *xb, short il, thread type4x4 & reg) {
|
||||
device const uint8_t * q = xb->qs;
|
||||
device const uint8_t * qh = xb->qh;
|
||||
|
||||
short is = (il/4) * 2;
|
||||
q = q + 32 * (il/4) + 16 * (il&1);
|
||||
qh = qh + 16 * (il&1);
|
||||
uint8_t ul = 1 << (il/2);
|
||||
il = il & 3;
|
||||
const uchar2 sc = get_scale_min_k4_just2(is, il/2, xb->scales);
|
||||
const float d = il < 2 ? xb->d : xb->d / 16.f;
|
||||
const float min = xb->dmin;
|
||||
const float dl = d * sc[0];
|
||||
const float ml = min * sc[1];
|
||||
|
||||
const ushort mask = il<2 ? 0x0F : 0xF0;
|
||||
const float qh_val = il<2 ? 16.f : 256.f;
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
reg[i/4][i%4] = dl * ((q[i] & mask) + (qh[i] & ul ? qh_val : 0)) - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_q6_K(device const block_q6_K *xb, short il, thread type4x4 & reg) {
|
||||
const half d_all = xb->d;
|
||||
device const uint8_t * ql = (device const uint8_t *)xb->ql;
|
||||
device const uint8_t * qh = (device const uint8_t *)xb->qh;
|
||||
device const int8_t * scales = (device const int8_t *)xb->scales;
|
||||
|
||||
ql = ql + 64*(il/8) + 32*((il/2)&1) + 16*(il&1);
|
||||
qh = qh + 32*(il/8) + 16*(il&1);
|
||||
float sc = scales[(il%2) + 2 * ((il/2))];
|
||||
il = (il/2) & 3;
|
||||
|
||||
const uint16_t kmask1 = il>1 ? (il>2 ? 192 : 48) : (il>0 ? 12 : 3);
|
||||
const uint16_t kmask2 = il>1 ? 0xF0 : 0x0F;
|
||||
const float coef = il>1 ? 1.f/16.f : 1.f;
|
||||
const float ml = d_all * sc * 32.f;
|
||||
const float dl = d_all * sc * coef;
|
||||
for (int i = 0; i < 16; ++i) {
|
||||
const half q = il&1 ? ((ql[i] & kmask2) | ((qh[i] & kmask1) << 2))
|
||||
: ((ql[i] & kmask2) | ((qh[i] & kmask1) << 4));
|
||||
reg[i/4][i%4] = dl * q - ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq2_xxs(device const block_iq2_xxs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
// each block of 32 needs 2 uint32_t's for the quants & scale, so 4 uint16_t's.
|
||||
device const uint16_t * q2 = xb->qs + 4*ib32;
|
||||
const uint32_t aux32_g = q2[0] | (q2[1] << 16);
|
||||
const uint32_t aux32_s = q2[2] | (q2[3] << 16);
|
||||
thread const uint8_t * aux8 = (thread const uint8_t *)&aux32_g;
|
||||
const float dl = d * (0.5f + (aux32_s >> 28)) * 0.25f;
|
||||
constant uint8_t * grid = (constant uint8_t *)(iq2xxs_grid + aux8[2*il+0]);
|
||||
uint8_t signs = ksigns_iq2xs[(aux32_s >> 14*il) & 127];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
grid = (constant uint8_t *)(iq2xxs_grid + aux8[2*il+1]);
|
||||
signs = ksigns_iq2xs[(aux32_s >> (14*il+7)) & 127];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[2+i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq2_xs(device const block_iq2_xs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint16_t * q2 = xb->qs + 4*ib32;
|
||||
const float dl = d * (0.5f + ((xb->scales[ib32] >> 4*il) & 0xf)) * 0.25f;
|
||||
constant uint8_t * grid = (constant uint8_t *)(iq2xs_grid + (q2[2*il+0] & 511));
|
||||
uint8_t signs = ksigns_iq2xs[q2[2*il+0] >> 9];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
grid = (constant uint8_t *)(iq2xs_grid + (q2[2*il+1] & 511));
|
||||
signs = ksigns_iq2xs[q2[2*il+1] >> 9];
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[2+i/4][i%4] = dl * grid[i] * (signs & kmask_iq2xs[i] ? -1.f : 1.f);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq3_xxs(device const block_iq3_xxs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint8_t * q3 = xb->qs + 8*ib32;
|
||||
device const uint16_t * gas = (device const uint16_t *)(xb->qs + QK_K/4) + 2*ib32;
|
||||
const uint32_t aux32 = gas[0] | (gas[1] << 16);
|
||||
const float dl = d * (0.5f + (aux32 >> 28)) * 0.5f;
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+0]);
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+1]);
|
||||
uint8_t signs = ksigns_iq2xs[(aux32 >> 14*il) & 127];
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * grid1[i] * (signs & kmask_iq2xs[i+0] ? -1.f : 1.f);
|
||||
reg[1][i] = dl * grid2[i] * (signs & kmask_iq2xs[i+4] ? -1.f : 1.f);
|
||||
}
|
||||
grid1 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+2]);
|
||||
grid2 = (constant uint8_t *)(iq3xxs_grid + q3[4*il+3]);
|
||||
signs = ksigns_iq2xs[(aux32 >> (14*il+7)) & 127];
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[2][i] = dl * grid1[i] * (signs & kmask_iq2xs[i+0] ? -1.f : 1.f);
|
||||
reg[3][i] = dl * grid2[i] * (signs & kmask_iq2xs[i+4] ? -1.f : 1.f);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq3_s(device const block_iq3_s * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint8_t * qs = xb->qs + 8*ib32;
|
||||
device const uint8_t * signs = xb->signs + 4*ib32 + 2*il;
|
||||
const uint8_t qh = xb->qh[ib32] >> 4*il;
|
||||
const float dl = d * (1 + 2*((xb->scales[ib32/2] >> 4*(ib32%2)) & 0xf));
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq3s_grid + (qs[4*il+0] | ((qh << 8) & 256)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq3s_grid + (qs[4*il+1] | ((qh << 7) & 256)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * grid1[i] * select(1, -1, signs[0] & kmask_iq2xs[i+0]);
|
||||
reg[1][i] = dl * grid2[i] * select(1, -1, signs[0] & kmask_iq2xs[i+4]);
|
||||
}
|
||||
grid1 = (constant uint8_t *)(iq3s_grid + (qs[4*il+2] | ((qh << 6) & 256)));
|
||||
grid2 = (constant uint8_t *)(iq3s_grid + (qs[4*il+3] | ((qh << 5) & 256)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[2][i] = dl * grid1[i] * select(1, -1, signs[1] & kmask_iq2xs[i+0]);
|
||||
reg[3][i] = dl * grid2[i] * select(1, -1, signs[1] & kmask_iq2xs[i+4]);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq2_s(device const block_iq2_s * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const float d = xb->d;
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint8_t * qs = xb->qs + 4*ib32 + 2*il;
|
||||
device const uint8_t * signs = qs + QK_K/8;
|
||||
const uint8_t qh = xb->qh[ib32] >> 4*il;
|
||||
const float dl = d * (0.5f + ((xb->scales[ib32] >> 4*il) & 0xf)) * 0.25f;
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq2s_grid + (qs[0] | ((qh << 8) & 0x300)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq2s_grid + (qs[1] | ((qh << 6) & 0x300)));
|
||||
for (int i = 0; i < 8; ++i) {
|
||||
reg[i/4+0][i%4] = dl * grid1[i] * select(1, -1, signs[0] & kmask_iq2xs[i]);
|
||||
reg[i/4+2][i%4] = dl * grid2[i] * select(1, -1, signs[1] & kmask_iq2xs[i]);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq1_s(device const block_iq1_s * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
const float d = xb->d;
|
||||
device const uint8_t * qs = xb->qs + 4*ib32 + 2*il;
|
||||
device const uint16_t * qh = xb->qh;
|
||||
const float dl = d * (2*((qh[ib32] >> 12) & 7) + 1);
|
||||
const float ml = dl * (qh[ib32] & 0x8000 ? -1 - IQ1S_DELTA : -1 + IQ1S_DELTA);
|
||||
const uint16_t h = qh[ib32] >> 6*il;
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((h << 8) & 0x700)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((h << 5) & 0x700)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * (grid1[i] & 0xf) + ml;
|
||||
reg[1][i] = dl * (grid1[i] >> 4) + ml;
|
||||
reg[2][i] = dl * (grid2[i] & 0xf) + ml;
|
||||
reg[3][i] = dl * (grid2[i] >> 4) + ml;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq1_m(device const block_iq1_m * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
device const uint16_t * sc = (device const uint16_t *)xb->scales;
|
||||
|
||||
iq1m_scale_t scale;
|
||||
scale.u16 = (sc[0] >> 12) | ((sc[1] >> 8) & 0x00f0) | ((sc[2] >> 4) & 0x0f00) | (sc[3] & 0xf000);
|
||||
const float d = scale.f16;
|
||||
|
||||
device const uint8_t * qs = xb->qs + 4*ib32 + 2*il;
|
||||
device const uint8_t * qh = xb->qh + 2*ib32 + il;
|
||||
|
||||
const float dl = d * (2*((sc[ib32/2] >> (6*(ib32%2)+3*il)) & 7) + 1);
|
||||
const float ml1 = dl * (qh[0] & 0x08 ? -1 - IQ1M_DELTA : -1 + IQ1M_DELTA);
|
||||
const float ml2 = dl * (qh[0] & 0x80 ? -1 - IQ1M_DELTA : -1 + IQ1M_DELTA);
|
||||
constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((qh[0] << 8) & 0x700)));
|
||||
constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((qh[0] << 4) & 0x700)));
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
reg[0][i] = dl * (grid1[i] & 0xf) + ml1;
|
||||
reg[1][i] = dl * (grid1[i] >> 4) + ml1;
|
||||
reg[2][i] = dl * (grid2[i] & 0xf) + ml2;
|
||||
reg[3][i] = dl * (grid2[i] >> 4) + ml2;
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq4_nl(device const block_iq4_nl * xb, short il, thread type4x4 & reg) {
|
||||
device const uint16_t * q4 = (device const uint16_t *)xb->qs;
|
||||
const float d = xb->d;
|
||||
uint32_t aux32;
|
||||
thread const uint8_t * q8 = (thread const uint8_t *)&aux32;
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
aux32 = ((q4[2*i] | (q4[2*i+1] << 16)) >> 4*il) & 0x0f0f0f0f;
|
||||
reg[i][0] = d * kvalues_iq4nl_f[q8[0]];
|
||||
reg[i][1] = d * kvalues_iq4nl_f[q8[1]];
|
||||
reg[i][2] = d * kvalues_iq4nl_f[q8[2]];
|
||||
reg[i][3] = d * kvalues_iq4nl_f[q8[3]];
|
||||
}
|
||||
}
|
||||
|
||||
template <typename type4x4>
|
||||
void dequantize_iq4_xs(device const block_iq4_xs * xb, short il, thread type4x4 & reg) {
|
||||
// il is 0...15 for QK_K = 256 => index of block of 32 is il/2
|
||||
const int ib32 = il/2;
|
||||
il = il%2;
|
||||
// il = 0 or 1. il = 0 processes the first 16 quants in a block of 32, il = 1 the second 16
|
||||
device const uint32_t * q4 = (device const uint32_t *)xb->qs + 4*ib32;
|
||||
const int ls = ((xb->scales_l[ib32/2] >> 4*(ib32%2)) & 0xf) | (((xb->scales_h >> 2*ib32) & 3) << 4);
|
||||
const float d = (float)xb->d * (ls - 32);
|
||||
uint32_t aux32;
|
||||
thread const uint8_t * q8 = (thread const uint8_t *)&aux32;
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
aux32 = (q4[i] >> 4*il) & 0x0f0f0f0f;
|
||||
reg[i][0] = d * kvalues_iq4nl_f[q8[0]];
|
||||
reg[i][1] = d * kvalues_iq4nl_f[q8[1]];
|
||||
reg[i][2] = d * kvalues_iq4nl_f[q8[2]];
|
||||
reg[i][3] = d * kvalues_iq4nl_f[q8[3]];
|
||||
}
|
||||
}
|
||||
|
||||
template<typename block_q, short nl, void (*dequantize_func)(device const block_q *, short, thread float4x4 &)>
|
||||
kernel void kernel_get_rows_q(
|
||||
device const void * src0,
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
#include "ggml-quants.h"
|
||||
#include "ggml-impl.h"
|
||||
#include "ggml-cpu-impl.h"
|
||||
|
||||
#include "ggml-cpu.h"
|
||||
|
||||
#include <math.h>
|
||||
#include <string.h>
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue